Responses to survey questions
| Paraphrased survey question | Response, median (25–75th percentiles)* | |||||
| Overall | Attending physicians | Resident physicians | Advanced practice providers (APP) | Nurses | Radiotherapy technologists (RTT) | |
| The study disrupted my clinical workflow† | 4 (4–5) | 4.5 (3.25–5) | 4 (4-4) | 3 (3–3.5) | 4 (3.25–4) | 4 (4–4.5) |
| Patients on the intervention were at high risk for acute care visits‡ | 2 (2–3) 13 not aware | 2 (2–3) | 2 (2–2) | 2 (2–2) | 2 (2–2) | 2.5 (2–3) |
| I was aware of my patients who were undergoing intervention | 2 (2–3) | 3.5 (2.25–5) | 2 (2–3) | 2 (1.5–2.5) | 2.5 (2–3) | 2 (2–3) |
| The study altered my clinical management‡ | 4 (3–4) 5 not aware | 4 (3.5–4) | 3 (3–3.5) | 4 (4–4) | 4 (4–4.75) | 4 (3–4.5) |
| I would implement the machine learning system routinely if the study is positive | 2 (1–3) | 2 (2–2) | 2 (1–3) | 3 (2–3) | 2 (1–2) | 2 (2–3) |
| My opinion of machine learning to assist with clinical care is now… | 3 (2–3) | 3 (2.25–3) | 2 (2–3) | 3 (2–3) | 3 (3–3) | 2 (2–3) |
| Patients understood the study after their first mandatory visit | 3 (2–3) | 3 (3–3) | 3 (2–3) | 3 (2.5–3) | 3 (2–3) | 3 (3–3.5) |
*Responses on a 5-point Likert-type scale ranging from 1 (strongly agree; much better) to 5 (strongly disagree; much worse).
†APPs, nurses and RTTs were most frequently directly involved in the supplemental visits.
‡Also included the option for respondents to indicate that they were not aware which patients were identified as high risk by the algorithm.